{"id":"https://openalex.org/W4403220659","doi":"https://doi.org/10.1145/3640457.3688140","title":"Scalable Cross-Entropy Loss for Sequential Recommendations with Large Item Catalogs","display_name":"Scalable Cross-Entropy Loss for Sequential Recommendations with Large Item Catalogs","publication_year":2024,"publication_date":"2024-10-08","ids":{"openalex":"https://openalex.org/W4403220659","doi":"https://doi.org/10.1145/3640457.3688140"},"language":"en","primary_location":{"id":"doi:10.1145/3640457.3688140","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640457.3688140","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3688140","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3688140","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107823380","display_name":"Gleb Mezentsev","orcid":"https://orcid.org/0009-0003-7591-3082"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Gleb Mezentsev","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Russian Federation"],"raw_orcid":"https://orcid.org/0009-0003-7591-3082","affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Russian Federation","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107823381","display_name":"Danil Gusak","orcid":"https://orcid.org/0009-0008-1238-6533"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]},{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Danil Gusak","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Russian Federation and HSE University, Russian Federation"],"raw_orcid":"https://orcid.org/0009-0008-1238-6533","affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Russian Federation and HSE University, Russian Federation","institution_ids":["https://openalex.org/I125989756","https://openalex.org/I118501908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004111307","display_name":"Ivan Oseledets","orcid":"https://orcid.org/0000-0003-2071-2163"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Ivan Oseledets","raw_affiliation_strings":["Artificial Intelligence Research Institute, Russian Federation and Skolkovo Institute of Science and Technology, Russian Federation"],"raw_orcid":"https://orcid.org/0000-0003-2071-2163","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Russian Federation and Skolkovo Institute of Science and Technology, Russian Federation","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010009492","display_name":"Evgeny Frolov","orcid":"https://orcid.org/0000-0003-3679-5311"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]},{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Evgeny Frolov","raw_affiliation_strings":["Artificial Intelligence Research Institute, Russian Federation; Skolkovo Institute of Science and Technology, Russian Federation and HSE University, Russian Federation","Artificial Intelligence Research Institute, Russian Federation"],"raw_orcid":"https://orcid.org/0000-0003-3679-5311","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Russian Federation; Skolkovo Institute of Science and Technology, Russian Federation and HSE University, Russian Federation","institution_ids":["https://openalex.org/I125989756","https://openalex.org/I118501908"]},{"raw_affiliation_string":"Artificial Intelligence Research Institute, Russian Federation","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.8953,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.96903524,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"475","last_page":"485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.676863968372345},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6339877843856812},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5510967373847961},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.4824386537075043},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36382371187210083},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.22134116291999817},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20233282446861267},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18056648969650269},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07497528195381165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.676863968372345},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6339877843856812},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5510967373847961},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.4824386537075043},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36382371187210083},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.22134116291999817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20233282446861267},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18056648969650269},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07497528195381165},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3640457.3688140","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640457.3688140","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3688140","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.18721","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.18721","pdf_url":"https://arxiv.org/pdf/2409.18721","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/159401","is_oa":false,"landing_page_url":"https://hdl.handle.net/1721.1/159401","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Association for Computing Machinery","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"doi:10.1145/3640457.3688140","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640457.3688140","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3688140","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403220659.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1976999215","https://openalex.org/W2001259128","https://openalex.org/W2027731328","https://openalex.org/W2152808281","https://openalex.org/W2171279286","https://openalex.org/W2510184840","https://openalex.org/W2626454364","https://openalex.org/W2783272285","https://openalex.org/W2963367478","https://openalex.org/W2980789587","https://openalex.org/W2984100107","https://openalex.org/W2996931760","https://openalex.org/W3012952868","https://openalex.org/W3083784942","https://openalex.org/W3088694469","https://openalex.org/W3089147479","https://openalex.org/W3102619277","https://openalex.org/W3111543999","https://openalex.org/W3119242082","https://openalex.org/W3153940464","https://openalex.org/W3154199194","https://openalex.org/W3156844209","https://openalex.org/W3185773347","https://openalex.org/W3195554589","https://openalex.org/W3201149665","https://openalex.org/W3206127589","https://openalex.org/W3210984903","https://openalex.org/W4226330269","https://openalex.org/W4296591843","https://openalex.org/W4296604471","https://openalex.org/W4306317272","https://openalex.org/W4313555196","https://openalex.org/W4385373545","https://openalex.org/W4385849288","https://openalex.org/W4386729798","https://openalex.org/W4386730515","https://openalex.org/W4389664922","https://openalex.org/W4403582629"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2994927414"],"abstract_inverted_index":{"Scalability":[0],"issue":[1],"plays":[2],"a":[3,62,103,134,162],"crucial":[4],"role":[5],"in":[6,27,40,69,156,189],"productionizing":[7],"modern":[8],"recommender":[9],"systems.":[10],"Even":[11],"lightweight":[12],"architectures":[13],"may":[14],"suffer":[15],"from":[16,48],"high":[17],"computational":[18],"overload":[19],"due":[20],"to":[21,121,166,169],"intermediate":[22],"calculations,":[23],"limiting":[24],"their":[25,176],"practicality":[26],"real-world":[28],"applications.":[29],"Specifically,":[30],"applying":[31],"full":[32],"Cross-Entropy":[33,65],"(CE)":[34],"loss":[35,67,78],"often":[36],"yields":[37],"state-of-the-art":[38],"performance":[39],"terms":[41],"of":[42,114,136,154,164],"recommendations":[43,93],"quality.":[44,94],"Still,":[45],"it":[46],"suffers":[47],"excessive":[49],"GPU":[50],"memory":[51,89,159],"utilization":[52],"when":[53],"dealing":[54],"with":[55,81],"large":[56,194],"item":[57],"catalogs.":[58],"This":[59,125],"paper":[60],"introduces":[61],"novel":[63],"Scalable":[64],"(SCE)":[66],"function":[68],"the":[70,76,110,115,130,137,141,152,170],"sequential":[71],"learning":[72],"setup.":[73],"It":[74],"approximates":[75],"CE":[77],"for":[79,186],"datasets":[80,150],"large-size":[82],"catalogs,":[83],"enhancing":[84],"both":[85],"time":[86],"efficiency":[87],"and":[88],"usage":[90,160],"without":[91],"compromising":[92],"Unlike":[95],"traditional":[96],"negative":[97],"sampling":[98],"methods,":[99],"our":[100],"approach":[101,181],"utilizes":[102],"selective":[104],"GPU-efficient":[105],"computation":[106],"strategy,":[107],"focusing":[108],"on":[109,148],"most":[111,119],"informative":[112],"elements":[113],"catalog,":[116],"particularly":[117],"those":[118],"likely":[120],"be":[122],"false":[123],"positives.":[124],"is":[126],"achieved":[127],"by":[128,161],"approximating":[129],"softmax":[131],"distribution":[132],"over":[133],"subset":[135],"model":[138],"outputs":[139],"through":[140],"maximum":[142],"inner":[143],"product":[144],"search.":[145],"Experimental":[146],"results":[147],"multiple":[149],"demonstrate":[151],"effectiveness":[153],"SCE":[155],"reducing":[157],"peak":[158],"factor":[163],"up":[165],"100":[167],"compared":[168],"alternatives,":[171],"retaining":[172],"or":[173],"even":[174],"exceeding":[175],"metrics":[177],"values.":[178],"The":[179],"proposed":[180],"also":[182],"opens":[183],"new":[184],"perspectives":[185],"large-scale":[187],"developments":[188],"different":[190],"domains,":[191],"such":[192],"as":[193],"language":[195],"models.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2024-10-09T00:00:00"}